Static analysis of energy consumption for LLVM IR programs

Abstract

Energy models can be constructed by characterizing the energy consumed by executing each instruction in a processor's instruction set. This can be used to determine how much energy is required to execute a sequence of assembly instructions, without the need to instrument or measure hardware. However, statically analyzing low-level program structures is hard, and the gap between the high-level program structure and the low-level energy models needs to be bridged. We have developed techniques for performing a static analysis on the intermediate compiler representations of a program. Specifically, we target LLVM IR, a representation used by modern compilers, including Clang. Using these techniques we can automatically infer an estimate of the energy consumed when running a function under different platforms, using different compilers. One of the challenges in doing so is that of determining an energy cost of executing LLVM IR program segments, for which we have developed two different approaches. When this information is used in conjunction with our analysis, we are able to infer energy formulae that characterize the energy consumption for a particular program. This approach can be applied to any languages targeting the LLVM toolchain, including C and XC or architectures such as ARM Cortex-M or XMOS xCORE, with a focus towards embedded platforms. Our techniques are validated on these platforms by comparing the static analysis results to the physical measurements taken from the hardware. Static energy consumption estimation enables energy-aware software development, without requiring hardware knowledge

Energy-Aware Software Engineering

“…[14,15] and also in Ref. [16]. The accuracy of energy consumption estimation at LLVM IR level is typically within 1-3% of that achieved using ISA-level models.…”

ENTRA: Whole-systems energy transparency

“…As mentioned, LLVM IR offers a good trade-off between analyzability and accuracy. In addition to using a generic approach based on CiaoPP and a translation to HC IR, the ENTRA project has experimented with an approach that uses similar analysis techniques but operates directly on the LLVM IR representation [36]. The advantage is that this approach can be integrated more directly in the LLVM toolchain; in principle it is applicable to any languages targeting LLVM.…”

Synchronous Reactive Nano-Kernels

“…This requires not only the minimization of energy consumption during system activity and in standby mode, but also the implementation of appropriate transitions between standby mode and the active mode to prevent premature chemical or physical degradation of the battery [2].…”